© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66219
    Prev
    Next
    INDEX
    Explanations

    advancing states or situations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on adverbs and other words used to add emphasis or degree to a statement (intensifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.64
    mädchen
    -1.59
     öde
    -1.57
    drück
    -1.55
     transak
    -1.48
     kultury
    -1.48
    bestimm
    -1.47
    förm
    -1.47
     pittores
    -1.45
    mittag
    -1.44
    POSITIVE LOGITS
     have
    2.64
     got
    2.39
     had
    2.27
     been
    2.19
     didn
    2.08
     want
    2.06
     get
    2.05
     need
    2.00
     saw
    1.99
     took
    1.95
    Activations Density 0.045%

    No Known Activations